Re: [External] : Re: [REGRESSION][v6.17-rc1]sched/fair: Bump sd->max_newidle_lb_cost when newidle balance fails

[Joseph Salisbury <joseph.salisbury@oracle.com>]

On 10/6/25 17:23, Chris Mason wrote:
> On 10/6/25 4:23 PM, Joseph Salisbury wrote:
>> Hi Chris,
>>
>> During testing, we are seeing a ~6% performance regression with the
>> upstream stable v6.12.43 kernel (And Oracle UEK
>> 6.12.0-104.43.4.el9uek.x86_64 kernel) when running the Phoronix
>> pts/apache benchmark with 100 concurrent requests [0].  The regression
>> is seen with the following hardware:
>>
>> PROCESSOR: Intel Xeon Platinum 8167M Core Count: 8 Thread Count: 16
>> Extensions: SSE 4.2 + AVX512CD + AVX2 + AVX + RDRAND + FSGSBASE Cache
>> Size: 16 MB Microcode: 0x1 Core Family: Cascade Lake
>>
>> After performing a bisect, we found that the performance regression was
>> introduced by the following commit:
>>
>> Stable v6.12.43: fc4289233e4b ("sched/fair: Bump sd->max_newidle_lb_cost
>> when newidle balance fails")
>> Mainline v6.17-rc1: 155213a2aed4 ("sched/fair: Bump
>> sd->max_newidle_lb_cost when newidle balance fails")
>>
>> Reverting this commit causes the performance regression to not exist.
>>
>> I was hoping to get your feedback, since you are the patch author.  Do
>> you think gathering any additional data will help diagnose this issue?
> Hi everyone,
>
> Peter, we've had a collection of regression reports based on this
> change, so it sounds like we need to make it less aggressive, or maybe
> we need to make the degrading of the cost number more aggressive?
>
> Joe (and everyone else who has hit this), can I talk you into trying the
> drgn from
> https://urldefense.com/v3/__https://lore.kernel.org/lkml/2fbf24bc-e895-40de-9ff6-5c18b74b4300@meta.com/__;!!ACWV5N9M2RV99hQ!Pm-G5L97VLtQdDRHad16cdOnEwHxyKGHd8U1FSLtAY-oy2pNcbmCjTS1XRjq-ypIoQdJGkE_12KkAr0$
>
> I'm curious if it degrades at all or just gets stuck up high.
>
> -chris
Hi Chris,

Thanks for the quick response!

Yes, I will try out the drgn from the link you posted and provide feedback.

Thanks,

Joe